About the hoshi ryoma tag
hoshi ryoma is a character tag that NovelAI Diffusion can use. On Danbooru it has 673 posts, and its best-rated still image scores 67. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws hoshi ryoma
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing hoshi ryoma in a prompt
Put the subject first, then this tag, then quality tags.
hoshi ryoma, solo, best quality, masterpiecewlop, hoshi ryoma, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Character from Danganronpa V3: Killing Harmony.
The former Ultimate Tennis Player. While he originally was very proficient in the sport, he had given up on using it professionally and ended up using his talent to kill Yakuza members with a variation of it he called "murder tennis". Prior to the game, these actions led him to Death Row. Ryouma is mostly standoffish because he doesn't want to get others involved with his past.
He is a short boy who wears a black leather jacket and blue striped pants. His brown hair is hidden under a horned blue hat. Has very prominent leg muscles.
Appearance
FAQ
Does NovelAI recognize hoshi ryoma?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from hoshi ryoma.
How do I write hoshi ryoma in a prompt?
Write "hoshi ryoma" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.